（關注公眾號設為標，獲取AI深度洞察）

全文 3,000字 | 閱讀約12分鐘

谷歌剛剛推出了他們家最聰明的AI模型——Gemini 2.5?。ㄔ囉茫篽ttps://aistudio.google.com/app/prompts/new_chat）這次上線的是2.5 Pro實驗版，它在各種行業測試中可是相當亮眼，甚至霸氣登頂了LMArena排行榜呢！

這個Gemini 2.5被稱為"會思考的模型"，它的特別之處在于不會急著回答問題，而是先在"腦子里"好好想一想，所以答案更準、表現更棒！不過，我們測試后發現，提示詞Gemini 2.5 Pro編碼能力測試顯示，整體動畫細節比較好，但是畫面豐富度沒有Claude 3.7和DeepSeek-V3 0324好。

但是，就在谷歌發布消息時，OpenAI立即推出了超強的"OpenAI 4o圖像生成功能"！OpenAI這次可是下了血本，他們的4o圖像生成技術在細節表現、創意想象和生成速度上都實現了質的飛躍，完全碾壓了谷歌的同類產品！

OpenAI的4o圖像生成功能不僅支持超高分辨率輸出，還能完美理解復雜提示詞，生成的圖像在美術風格、光影效果和場景構建上都達到了前所未有的水平。更令人驚嘆的是，它的生成速度比之前的模型快了整整3倍，用戶體驗得到了極大提升！

業內人士紛紛表示，OpenAI這次的圖像生成功能升級不只是單純的技術更新，更是向谷歌發起的全面挑戰。OpenAI顯然不甘落后，正集中全部火力與谷歌一較高下。這場AI巨頭之間的"軍備競賽"可真是越來越精彩了，對我們用戶來說，這種良性競爭帶來的技術進步簡直不要太爽！看來AI界的"卷王競爭"又進入了白熱化階段。

提示詞：A wide image taken with a phone of a glass whiteboard, in a room overlooking the Bay Bridge. The field of view shows a woman writing, sporting a tshirt wiith a large OpenAI logo. The handwriting looks natural and a bit messy, and we see the photographer's reflection.

The text reads:

(left) "Transfer between Modalities:

Suppose we directly model p(text, pixels, sound) [equation] with one big autoregressive transformer.

Pros:

• image generation augmented with vast world knowledge

• next-level text rendering

• native in-context learning

• unified post-training stack

Cons:

• varying bit-rate across modalities

• compute not adaptive"

(Right) "Fixes:

• model compressed representations

• compose autoregressive prior with a powerful decoder"

On the bottom right of the board, she draws a diagram: "tokens -> [transformer] -> [diffusion] -> pixels"

提示詞：selfie view of the photographer, as she turns around to high five him

圖像生成，變得更實用

從原始洞穴壁畫到現代信息圖，人類自古就善用圖像來交流、說服和分析，而不僅僅是用來裝飾。當今的生成模型雖然可以打造出超現實、令人驚艷的畫面，但面對日常信息傳遞所需的基礎圖像，如徽標、圖表等，仍顯力不從心。事實上，當圖像配合能喚起共同語言與經驗的符號，它們就能傳達極其精準的含義。

GPT-4o 圖像生成能力在文本呈現、指令響應及上下文理解方面表現尤為出色，它可以調用自身龐大的知識庫和對話上下文信息，甚至還能對上傳的圖像進行改造，或從中汲取靈感。這一切讓你能更輕松地將想象變為圖像，使視覺溝通更高效，也標志著圖像生成邁向更實用、更精準、更強大的全新階段。

一、圖像中的文字表達

一張圖能勝過千言萬語，但恰到好處地加入幾行文字，往往能為圖像賦予更深層的含義。4o 精準融合圖像與文字符號的能力，讓圖像生成成為真正意義上的視覺溝通工具。

提示詞：Create a photorealistic image of two witches in their 20s (one ash balayage, one with long wavy auburn hair) reading a street sign.

Context: a city street in a random street in Williamsburg, NY with a pole covered entirely by numerous detailed street signs (e.g., street sweeping hours, parking permits required, vehicle classifications, towing rules), including few ridiculous signs at the middle: (paraphrase it to make these legitimate street signs)"Broom Parking for Witches Not Permitted in Zone C" and "Magic Carpet Loading and Unloading Only (15-Minute Limit)" and "Reindeer Parking by Permit Only (Dec 24–25)\n Violators will be placed on Naughty List." The signpost is on the right of a street. Do not repeat signs. Signs must be realistic.

Characters: one witch is holding a broom and the other has a rolled-up magic carpet. They are in the foreground, back slightly turned towards the camera and head slightly tilted as they scrutinize the signs.

Composition from background to foreground: streets + parked cars + buildings -> street sign -> witches. Characters must be closest to the camera taking the shot

提示詞：photo of a delightful wedding invitation on a tasteful wooden desk. The card is hefty, with eggshell textures, and beautiful embossings, with elegant decorations abstractly representing the couple tastefully integrated into the designs. Iconography is used, but sparingly and in a minimalist way. perfect typesetting.

"You are cordially invited to the long-awaited union of

Image and Text

After years of flirting and collaboration they are finally becoming One.

Together at last, in GPT?4o, they now speak the same language — where a whisper becomes a masterpiece, and a prompt becomes a picture.

Please join us in celebrating this magical multimodal matrimony where imagination knows no bounds.

Date: March 25, 2025 Location: chatgpt.com Dress Code: Pixels or Prose

With love, OpenAI"

perfect typesetting.

二、支持多輪對話的圖像生成

圖像生成已深度集成進 GPT?4o，這意味著你可以像對話一樣自然地迭代圖像創作。GPT?4o 能結合聊天中的圖像和文字上下文，保持風格與內容的一致性。例如，當你在設計一款游戲角色時，角色的形象在多輪修改中依然連貫統一，讓創作過程更加順暢高效。

三、精準響應提示

GPT?4o 的圖像生成對提示指令響應精準，細節處理到位。相比之下，其他系統在處理 5 至 8 個物體時就已捉襟見肘，而 GPT?4o 可輕松應對 10 至 20 個不同物體的復雜場景。得益于對物體屬性與相互關系的更強綁定，用戶能夠更好地掌控生成圖像的結構與內容。

提示詞：A square image containing a 4 row by 4 column grid containing 16 objects on a white background. Go from left to right, top to bottom. Here's the list:

1. a blue star

2. red triangle

3. green square

4. pink circle

5. orange hourglass

6. purple infinity sign

7. black and white polka dot bowtie

8. tiedye "42"

9. an orange cat wearing a black baseball cap

10. a map with a treasure chest

11. a pair of googly eyes

12. a thumbs up emoji

13. a pair of scissors

14. a blue and white giraffe

15. the word "OpenAI" written in cursive

16. a rainbow-colored lightning bolt

提示詞：Times Square in New York City in the afternoon, with no people, vehicles, or illuminated billboards.

四、上下文理解能力

GPT?4o 可讀取并理解用戶上傳的圖像，將其細節融入當前對話背景，在生成圖像時做到有據可依、貼合語境。

五、融合世界知識

借助原生圖像生成，GPT?4o 能將其在文本與圖像兩方面的理解無縫連接，展現出更聰明、更高效的表現力。

提示詞：Make me a professionally shot photorealistic diagram of the top selling cocktails in my bar with recipes labeled on each drink.

put the recipes on handwritten cards in front of each drink.

the cards are brown, and the text is black.

background is white

Title is "4 most popular cocktails"

提示詞：make a visual infographic describing why SF is so foggy

六、逼真表現與風格適配

模型在多種圖像風格的訓練數據上進行學習，因此能自然生成或轉換圖像，既真實又具風格多樣性。

提示詞：A candid paparazzi-style photo of Karl Marx hurriedly walking through the parking lot of the Mall of America, glancing over his shoulder with a startled expression as he tries to avoid being photographed. He’s clutching multiple glossy shopping bags filled with luxury goods. His coat flutters behind him in the wind, and one of the bags is swinging as if he’s mid-stride. Blurred background with cars and a glowing mall entrance to emphasize motion. Flash glare from the camera partially overexposes the image, giving it a chaotic, tabloid feel.

提示詞：Best of 1 | Generate an portrait ad on a solid pastel background.

In solid white san serif text, "ChatGPT image generation" in the top left, about a third of the way down.

In solid white san serif text, "Form follows function", in the bottom right, about a third of the way up.

In the background, put a photo of a really sleek, modern sculpture. It should gradually transition from a wireframe sketch on the left to the fully photorealistic version on the right.

At the very bottom, in medium-small text, say "This entire poster was generated by ChatGPT image generation."

七、模型當前局限

盡管 GPT?4o 圖像生成功能實現了重大突破，但我們也清楚它仍存在不少值得關注的限制，這些問題將在未來的模型迭代中逐步解決。主要包括：

• 圖像裁剪問題：在構圖邊緣或內容密集時，模型容易誤剪掉關鍵元素，影響整體效果。

• 生成幻覺：有時模型會憑空“想象”出不存在的細節或物體，出現不符合現實的圖像內容。

• 對象屬性錯配：當指令中涉及多個對象及其屬性組合時，模型可能出現物體與特征對應混亂的問題。

• 圖表生成不夠精準：在繪制結構清晰、數據要求嚴格的圖表時，輸出可能出現誤差或比例不一致。

• 多語言文本表現力有限：雖然支持非英語文字生成，但在圖像中呈現如中文、阿拉伯文等語言時，有時會出現排版錯亂或字符變形。

• 圖像編輯控制不足：模型在修改或重繪圖像細節方面的精確性仍有提升空間，尤其在精細區域。

• 小字體信息表達受限：圖像中如需展示密集文本或小字號信息，容易出現模糊、重疊、無法辨識等問題。

從今天起，GPT?4o 圖像生成功能將在 ChatGPT 中全面上線，成為默認圖像生成工具，率先開放給 Plus、Pro、Team 和免費用戶使用，Enterprise 企業版和 Edu 教育版用戶也將在不久之后陸續獲得訪問權限。此外，這項功能也已集成進 Sora。若你仍偏愛 DALL·E，也無需擔心——它依然可以通過專屬的 DALL·E GPT 使用。

開發者將在未來幾周內，通過 API 接入 GPT?4o 進行圖像生成。

使用 GPT?4o 生成和定制圖像非常便捷，就像和它聊天一樣自然——只需描述你想要的內容，包括畫面比例、具體色值（如 hex 色碼），或是否需要透明背景等細節。由于模型輸出更為細膩，生成過程相對耗時，通常需要約一分鐘完成。

星標公眾號， 點這里 1. 點擊右上角 2. 點擊"設為星標" ← AI深度研究員 ? ← 設為星標

原文鏈接：https://openai.com/index/introducing-4o-image-generation/

來源：官方媒體/網絡新聞

排版：Atlas

編輯：深思

主編：圖靈